huggingface/optimum-nvidia

TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.

🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimization tools

https://wavespeed.ai/ Best inference performance optimization framework for HuggingFace Diffusers on NVIDIA GPUs.

Transformer related optimization, including BERT, GPT

AMD related optimizations for transformer models

Easy and lightning fast training of 🤗 Transformers on Habana Gaudi processor (HPU)

A highly optimized LLM inference acceleration engine for Llama and its variants.

~1300 line, minimal, extensible LLM inference engine built from scratch.

Accelerate your Hugging Face Transformers 7.6-9x. Native to Hugging Face and PyTorch.